template<typename AFloat = Double_t>
class TMVA::DNN::TCuda< AFloat >

The TCuda architecture class.

Low-level interface class for CUDA computing architectures. Contains as public types the declaration of the scalar, matrix and buffer types for this architecture as well as the remaining functions in the low-level interface in the form of static members.

Definition at line 40 of file Cuda.h.

Public Types
using	DeviceBuffer_t = TCudaDeviceBuffer< AFloat >

using	HostBuffer_t = TCudaHostBuffer< AFloat >

using	Matrix_t = TCudaMatrix< AFloat >

using	Scalar_t = AFloat

Static Public Member Functions
Forward Propagation
Low-level functions required for the forward propagation of activations through the network.
static void	MultiplyTranspose (TCudaMatrix< AFloat > &output, const TCudaMatrix< AFloat > &input, const TCudaMatrix< AFloat > &weights)
	Matrix-multiply `input` with the transpose of and write the results into `output`. More...

static void	AddRowWise (TCudaMatrix< AFloat > &output, const TCudaMatrix< AFloat > &biases)
	Add the vectors biases row-wise to the matrix output. More...

Backward Propagation
Low-level functions required for the forward propagation of activations through the network.
static void	Backward (TCudaMatrix< AFloat > &activationGradientsBackward, TCudaMatrix< AFloat > &weightGradients, TCudaMatrix< AFloat > &biasGradients, TCudaMatrix< AFloat > &df, const TCudaMatrix< AFloat > &activationGradients, const TCudaMatrix< AFloat > &weights, const TCudaMatrix< AFloat > &activationBackward)
	Perform the complete backward propagation step. More...

static void	ScaleAdd (TCudaMatrix< AFloat > &A, const TCudaMatrix< AFloat > &B, Scalar_t beta=1.0)
	Adds a the elements in matrix B scaled by c to the elements in the matrix A. More...

static void	Copy (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)
	Copy the elements of matrix A into matrix B. More...

Activation Functions
For each activation function, the low-level interface contains two routines. One that applies the acitvation function to a matrix and one that evaluate the derivatives of the activation function at the elements of a given matrix and writes the results into the result matrix.
static void	Identity (TCudaMatrix< AFloat > &B)

static void	IdentityDerivative (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)

static void	Relu (TCudaMatrix< AFloat > &B)

static void	ReluDerivative (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)

static void	Sigmoid (TCudaMatrix< AFloat > &B)

static void	SigmoidDerivative (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)

static void	Tanh (TCudaMatrix< AFloat > &B)

static void	TanhDerivative (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)

static void	SymmetricRelu (TCudaMatrix< AFloat > &B)

static void	SymmetricReluDerivative (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)

static void	SoftSign (TCudaMatrix< AFloat > &B)

static void	SoftSignDerivative (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)

static void	Gauss (TCudaMatrix< AFloat > &B)

static void	GaussDerivative (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)

Loss Functions
Loss functions compute a scalar value given the `output` of the network for a given training input and the expected network prediction `Y` that quantifies the quality of the prediction. For each function also a routing that computes the gradients (suffixed by Gradients) must be provided for the starting of the backpropagation algorithm.
static AFloat	MeanSquaredError (const TCudaMatrix< AFloat > &Y, const TCudaMatrix< AFloat > &output)

static void	MeanSquaredErrorGradients (TCudaMatrix< AFloat > &dY, const TCudaMatrix< AFloat > &Y, const TCudaMatrix< AFloat > &output)

static AFloat	CrossEntropy (const TCudaMatrix< AFloat > &Y, const TCudaMatrix< AFloat > &output)
	Sigmoid transformation is implicitly applied, thus `output` should hold the linear activations of the last layer in the net. More...

static void	CrossEntropyGradients (TCudaMatrix< AFloat > &dY, const TCudaMatrix< AFloat > &Y, const TCudaMatrix< AFloat > &output)

Output Functions
Output functions transform the activations `output` of the output layer in the network to a valid prediction `YHat` for the desired usage of the network, e.g. the identity function for regression or the sigmoid transformation for two-class classification.
static void	Sigmoid (TCudaMatrix< AFloat > &YHat, const TCudaMatrix< AFloat > &)

Regularization
For each regularization type two functions are required, one named `<Type>Regularization` that evaluates the corresponding regularization functional for a given weight matrix and the `Add<Type>RegularizationGradients`, that adds the regularization component in the gradients to the provided matrix.
static AFloat	L1Regularization (const TCudaMatrix< AFloat > &W)

static void	AddL1RegularizationGradients (TCudaMatrix< AFloat > &A, const TCudaMatrix< AFloat > &W, AFloat weightDecay)

static AFloat	L2Regularization (const TCudaMatrix< AFloat > &W)

static void	AddL2RegularizationGradients (TCudaMatrix< AFloat > &A, const TCudaMatrix< AFloat > &W, AFloat weightDecay)

Initialization
For each initialization method, one function in the low-level interface is provided. The naming scheme is Initialize<Type> for a given initialization method Type.
static void	InitializeGauss (TCudaMatrix< AFloat > &A)

static void	InitializeUniform (TCudaMatrix< AFloat > &A)

static void	InitializeIdentity (TCudaMatrix< AFloat > &A)

static void	InitializeZero (TCudaMatrix< AFloat > &A)

Dropout
static void	Dropout (TCudaMatrix< AFloat > &A, AFloat p)
	Apply dropout with activation probability `p` to the given matrix `A` and scale the result by reciprocal of `p`. More...

Additional Arithmetic Functions
Additional arithmetic on CUDA matrices used to implement the low-level interface.
static void	Multiply (TCudaMatrix< AFloat > &C, const TCudaMatrix< AFloat > &A, const TCudaMatrix< AFloat > &B)
	Standard multiplication of two matrices `A` and `B` with the result being written into C. More...

static void	TransposeMultiply (TCudaMatrix< AFloat > &output, const TCudaMatrix< AFloat > &input, const TCudaMatrix< AFloat > &Weights)
	Matrix multiplication of two matrices `A` and `B^T` (transposed) with the result being written into C. More...

static void	Hadamard (TCudaMatrix< AFloat > &A, const TCudaMatrix< AFloat > &B)
	In-place Hadamard (element-wise) product of matrices `A` and `B` with the result being written into `A`. More...

static void	SumColumns (TCudaMatrix< AFloat > &B, const TCudaMatrix< AFloat > &A)
	Sum columns of (m x n) matrixx `A` and write the results into the first m elements in `A`. More...

static AFloat	Sum (const TCudaMatrix< AFloat > &A)
	Compute the sum of all elements in `A`. More...

#include <TMVA/DNN/Architectures/Cuda.h>